A Unified Multimodal Deep Learning System for Robust Deep-fake Analysis

Read full text Summarise with VIRAT
Authors: B.V.Poorna Sree, D. Yashwanth, G.Raja, A.Hemanth kumar, Prof.(Dr.)Ravi Kiran
Cited by: 0
References: 9

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Deepfake media generated by generative adversarial networks (GANs) and neural voice synthesis pose an escalating threat to information integrity. This paper presents a multimodal deepfake detection system that jointly analyses video frames, facial images, and audio waveforms using three specialized deep learning branches: a GoogLeNet-based visual feature extractor coupled with an LSTM for temporal video modelling, a GoogLeNet image classifier with Grad-CAM explainability, and a four-layer convolutional neural network (CNN) trained on log-mel spectrograms for audio deepfake detection. A weighted fusion layer combines per-modality softmax scores into a single fakeness probability with a configurable decision threshold. The audio CNN achieves 94.2% test accuracy on binary real/fake classification; multimodal fusion further improves detection to 96.3% accuracy with F1- score 0.963. An interactive Streamlit application delivers realtime predictions with Grad-CAM attention overlays for analyst interpretability

Fields of Study & Subjects

Digital Media Forensic Detection Misinformation and Its Impacts Generative Adversarial Networks and Image Synthesis

Publication details

Journal / source
International Journal of Engineering Research and Science & Technology
Volume
22
Issue
1(2)
Pages
219–223
Publication date
28 March 2026
Language
EN